Reasoning and Retrieval for Complex Semi-structured Tables via Reinforced Relational Data Transformation

We introduce TabFormer, a framework that normalizes diverse semi-structured tables into relational data via large language models to facilitate various table retrieval and reasoning tasks. Our approach employs a chain-of-thought methodology, transforming one or multiple tables through a sequence of soft operations. Compared to existing operators that are sensitive and brittle to human-induced artifacts in real-world tables, soft operators are designed with greater flexibility to accommodate diverse formatting variations.